Related papers: AssemblyHands: Towards Egocentric Activity Underst…
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles. Participants work without fixed instructions, and the sequences feature rich and natural variations…
Bimanual human activities inherently involve coordinated movements of both hands and body. However, the impact of this coordination in activity understanding has not been systematically evaluated due to the lack of suitable datasets. Such…
3D hand pose estimation in everyday egocentric images is challenging for several reasons: poor visual signal (occlusion from the object of interaction, low resolution & motion blur), large perspective distortion (hands are close to the…
This report introduce our work on Egocentric 3D Hand Pose Estimation workshop. Using AssemblyHands, this challenge focuses on egocentric 3D hand pose estimation from a single-view image. In the competition, we adopt ViT based backbones and…
We interact with the world with our hands and see it through our own (egocentric) perspective. A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion…
Hand pose estimation from egocentric video has broad implications across various domains, including human-computer interaction, assistive technologies, activity recognition, and robotics, making it a topic of significant research interest.…
We tackle the problem of estimating the 3D pose of an individual's upper limbs (arms+hands) from a chest mounted depth-camera. Importantly, we consider pose estimation during everyday interactions with objects. Past work shows that strong…
Visual segmentation has seen tremendous advancement recently with ready solutions for a wide variety of scene types, including human hands and other body parts. However, focus on segmentation of human hands while performing complex tasks,…
Action recognition is essential for egocentric video understanding, allowing automatic and continuous monitoring of Activities of Daily Living (ADLs) without user effort. Existing literature focuses on 3D hand pose input, which requires…
We present AnyHand, a large-scale synthetic dataset designed to advance the state of the art in 3D hand pose estimation from both RGB-only and RGB-D inputs. While recent works with foundation approaches have shown that an increase in the…
Color-based two-hand 3D pose estimation in the global coordinate system is essential in many applications. However, there are very few datasets dedicated to this task and no existing dataset supports estimation in a non-laboratory…
This report describes our 1st place solution to ECCV 2022 challenge on Human Body, Hands, and Activities (HBHA) from Egocentric and Multi-view Cameras (hand pose estimation). In this challenge, we aim to estimate global 3D hand poses from…
Understanding social interactions from egocentric views is crucial for many applications, ranging from assistive robotics to AR/VR. Key to reasoning about interactions is to understand the body pose and motion of the interaction partner…
Egocentric videos offer fine-grained information for high-fidelity modeling of human behaviors. Hands and interacting objects are one crucial aspect of understanding a viewer's behaviors and intentions. We provide a labeled dataset…
In this survey, we present a systematic review of 3D hand pose estimation from the perspective of efficient annotation and learning. 3D hand pose estimation has been an important research area owing to its potential to enable various…
Egocentric 3D hand pose estimation and gesture recognition are essential for immersive augmented/virtual reality, human-computer interaction, and robotics. However, conventional frame-based cameras suffer from motion blur and limited…
With the emergence of collaborative robots (cobots), human-robot collaboration in industrial manufacturing is coming into focus. For a cobot to act autonomously and as an assistant, it must understand human actions during assembly. To…
In this paper we introduce a large-scale hand pose dataset, collected using a novel capture method. Existing datasets are either generated synthetically or captured using depth sensors: synthetic datasets exhibit a certain level of…
Hand pose represents key information for action recognition in the egocentric perspective, where the user is interacting with objects. We propose to improve egocentric 3D hand pose estimation based on RGB frames only by using pseudo-depth…
We present EgoHumans, a new multi-view multi-human video benchmark to advance the state-of-the-art of egocentric human 3D pose estimation and tracking. Existing egocentric benchmarks either capture single subject or indoor-only scenarios,…